Canonical Polyadic Decomposition and Deep Learning for Machine Fault Detection

TL;DR

This paper introduces a tensor decomposition-based denoising method to improve unsupervised machine fault detection from acoustic signals, enhancing reliability in industrial monitoring.

Contribution

It proposes a novel Non-negative CP tensor decomposition technique tailored for spectral data to effectively denoise stationary sound signals in machine fault detection.

Findings

Denoising improves anomaly detection accuracy.

Method performs well on MIMII benchmark dataset.

Enhances reliability of sound-based industrial monitoring.

Abstract

Acoustic monitoring for machine fault detection is a recent and expanding research path that has already provided promising results for industries. However, it is impossible to collect enough data to learn all types of faults from a machine. Thus, new algorithms, trained using data from healthy conditions only, were developed to perform unsupervised anomaly detection. A key issue in the development of these algorithms is the noise in the signals, as it impacts the anomaly detection performance. In this work, we propose a powerful data-driven and quasi non-parametric denoising strategy for spectral data based on a tensor decomposition: the Non-negative Canonical Polyadic (CP) decomposition. This method is particularly adapted for machine emitting stationary sound. We demonstrate in a case study, the Malfunctioning Industrial Machine Investigation and Inspection (MIMII) baseline, how the use of our denoising strategy leads to a sensible improvement of the unsupervised anomaly detection. Such approaches are capable to make sound-based monitoring of industrial processes more reliable.